CN117895899B - Photovoltaic panel cleanliness detection method and system - Google Patents
Photovoltaic panel cleanliness detection method and system Download PDFInfo
- Publication number
- CN117895899B CN117895899B CN202410303697.3A CN202410303697A CN117895899B CN 117895899 B CN117895899 B CN 117895899B CN 202410303697 A CN202410303697 A CN 202410303697A CN 117895899 B CN117895899 B CN 117895899B
- Authority
- CN
- China
- Prior art keywords
- photovoltaic panel
- cleanliness
- cleanliness detection
- photovoltaic
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003749 cleanliness Effects 0.000 title claims abstract description 123
- 238000001514 detection method Methods 0.000 title claims abstract description 99
- 238000002310 reflectometry Methods 0.000 claims abstract description 50
- 238000004140 cleaning Methods 0.000 claims abstract description 40
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims description 30
- 239000000428 dust Substances 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000009736 wetting Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
- H02S50/10—Testing of PV devices, e.g. of PV modules or single PV cells
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
- G01N2021/945—Liquid or solid deposits of macroscopic size on surfaces, e.g. drops, films, or clustered contaminants
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a method and a system for detecting the cleanliness of a photovoltaic panel, which relate to the technical field of cleanliness detection, and the method comprises the following steps: dividing a photovoltaic power station into m areas, wherein each area at least comprises a photovoltaic panel, setting fixed shooting points, and acquiring images of the photovoltaic panels in each area to obtain photovoltaic panel images in each area; preprocessing the obtained photovoltaic panel image to obtain cleaning characteristic information in the photovoltaic panel image; acquiring weather data of all areas, and measuring the reflectivity of the photovoltaic panels in all areas; calculating weather change data and reflectivity change data of all areas; constructing a cleanliness detection model based on the weather change data, the reflectivity change data and the cleaning characteristic information; and detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result. And the weather change and the reflection condition of the surface of the photovoltaic panel are analyzed, so that errors existing in the detection of the cleanliness of the photovoltaic panel by using machine vision are further reduced.
Description
Technical Field
The invention relates to the technical field of cleanliness detection, in particular to a method and a system for detecting the cleanliness of a photovoltaic panel.
Background
The cleanliness of the photovoltaic panel has an important influence on both its power generation efficiency and its lifetime. With the rapid development of photovoltaic power generation, detection and maintenance of the cleanliness of photovoltaic panels is becoming increasingly important. Traditionally, the cleanliness detection of photovoltaic panels has relied primarily on visual inspection or surface soil detection using simple tools. However, with the increase in the number and the wide distribution of photovoltaic panels, the conventional detection method has problems of low efficiency, high dependence on human resources and insufficient accuracy. Therefore, the method for detecting the cleanliness of the photovoltaic panel by adopting the machine vision and unmanned aerial vehicle technology is generated, the existing technology for detecting the cleanliness of the photovoltaic panel is usually only aimed at the cleanliness of the photovoltaic panel, and the influence of environmental and weather changes and the reflection condition of the surface of the photovoltaic panel on the detection of the cleanliness of the photovoltaic panel by using the machine vision is not considered.
The patent with the publication number CN115085653A discloses an automatic cleaning device with the function of detecting the cleanliness of a photovoltaic panel, which comprises two groups of telescopic supporting frames and a frame arranged between the tops of the two groups of telescopic supporting frames, wherein the inner side of the frame is connected with a cleaning assembly in a sliding manner, and the cleaning assembly moves left and right on the inner side of the frame through a driving mechanism; the cleaning component comprises a sliding plate sliding on the inner side of the frame, a blowing device connected below the sliding plate through a vertical plate, a horizontal plate fixed on one side of the vertical plate and an atomizer arranged at the bottom of the horizontal plate, and relates to the technical field of photovoltaic plates. When the photovoltaic panel is cleaned, the atomizer wets the photovoltaic panel, and then the dust after wetting is purged by the atomizer, so that dust cannot be raised after wetting, the dust is prevented from falling on the photovoltaic panel for the second time, and the cleaning quality of the photovoltaic panel is improved.
The utility model discloses a photovoltaic board cleanliness detection and alarm method and device as disclosed in the patent with publication number CN113794444A, the device includes casing and built-in circuit, voltage measurement port and the electric current measurement port that establish on the casing, voltage measurement port and electric current measurement port are connected with the output line of photovoltaic board through the wire, built-in circuit includes detection module, control processing module, alarm module, automatic start-stop module and display module, detection module includes photosensitive sensor, voltage sensor, current sensor, automatic start-stop module includes humidity transducer, control processing module includes the singlechip, control processing module's output and alarm module, display module connect, alarm module includes bee calling organ and alarm lamp, display module includes the display screen. According to the invention, the photovoltaic panel cleanliness is monitored by detecting the illumination intensity in real time and the voltage and current generated by the photovoltaic panel in real time, so that the working efficiency is greatly improved, and the safety of the whole device is ensured by the automatic start-stop module.
The problems presented in the background art exist in the above patents: the impact of environmental and weather changes and photovoltaic panel surface reflection conditions on the use of machine vision for photovoltaic panel cleanliness detection is not considered. In order to solve the problem, the invention provides a method and a system for detecting the cleanliness of a photovoltaic panel.
Disclosure of Invention
Aiming at the defects of the prior art, the invention mainly aims to provide a method and a system for detecting the cleanliness of a photovoltaic panel, which can effectively solve the problems in the background art. The specific technical scheme of the invention is as follows:
The method for detecting the cleanliness of the photovoltaic panel comprises the following specific steps:
S1, dividing a photovoltaic power station into m areas, wherein each area at least comprises a photovoltaic panel, setting fixed shooting points, and acquiring images of the photovoltaic panels in each area to obtain the images of the photovoltaic panels in each area;
s2, preprocessing the obtained photovoltaic panel image to obtain cleaning characteristic information in the photovoltaic panel image;
s3, weather data of all areas are obtained, and reflectivity of the photovoltaic panels in all areas is measured;
s4, calculating weather change data and reflectivity change data of all areas based on the step S3;
s5, constructing a cleanliness detection model based on weather change data, reflectivity change data and cleaning characteristic information;
And S6, detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result.
Specifically, the step of acquiring the photovoltaic panel image of each region in S1 includes acquiring the photovoltaic panel images of each region at n times.
Specifically, the preprocessing in S2 includes: image denoising operation and image enhancement operation.
In this embodiment, the step S2 of acquiring the cleaning feature information in the photovoltaic panel image specifically includes the following steps:
s201, calculating a dust coverage value of the photovoltaic panel based on the photovoltaic panel images of each region at n moments;
S202, threshold segmentation is carried out on the preprocessed photovoltaic panel images at n times in each region, the photovoltaic panel images are segmented into dirt images and background images, and dirt change values of the photovoltaic panels are calculated;
And S203, taking the dust coverage value of the photovoltaic panel and the dirt change value of the photovoltaic panel as cleaning characteristic information.
Specifically, the step of obtaining weather data of all the areas in S3 includes: acquiring wind speed, humidity and air quality indexes of each region at n moments; the measuring the reflectivity of the photovoltaic panel in all areas includes: the reflectivity of the photovoltaic panel was measured at n times per zone.
Specifically, the step S201 includes the following specific steps:
s2011, traversing all pixel points in the photovoltaic panel image at the jth moment of the ith area, and acquiring color vectors of all pixel points, wherein i is any one of 1 to m, and j is any one of 1 to n;
S2012, setting the Q pixel points in the photovoltaic panel image at the jth moment of the ith area, wherein the color vector of the qth pixel point is as follows Wherein/>For the color value of the red channel in the color vector of the q-th pixel point,/>For the color value of the green channel in the color vector of the q-th pixel point,/>A color value of a blue channel in a color vector for a qth pixel, Q being any one of 1 to Q;
S2013, calculating the dust coverage value of the photovoltaic panel at the j-th moment of the i-th area Wherein Q is any one of 1 to Q, when q=1,/>、/>、/>All 0.
Specifically, the specific steps for calculating the dirt change value of the photovoltaic panel include:
s2021, setting a pixel segmentation threshold value as T, and carrying out threshold segmentation on the preprocessed photovoltaic panel images at n times in each region;
S2022, carrying out graying treatment on the photovoltaic panel image at n times in each region, and extracting gray values corresponding to all pixel points in the image, wherein the gray value of the q-th pixel point in the photovoltaic panel image at the j-th time in the ith region is ；
S2023, counting the pixel points with the gray values smaller than or equal to the pixel segmentation threshold T and the pixel points with the gray values larger than the pixel segmentation threshold T; setting total Q1 pixel points with gray values less than or equal to the pixel division threshold T, wherein the gray value of the Q1 pixel point isQ1 is any one of 1 to Q1; the total number of the pixel points with the Q2 gray values larger than the pixel division threshold T is Q2, wherein the gray value of the Q2 th pixel point is/>Q2 is any one of 1 to Q2;
s2024 calculating the intraclass variance using the intraclass variance calculation formula Acquiring a pixel segmentation threshold T with the smallest intra-class variance as a dirt segmentation threshold of the photovoltaic panel image at the jth moment of the ith area; wherein the intra-class variance calculation formula is；
S2025, based on the dirt segmentation threshold T of the photovoltaic panel image at the jth moment in the ith area, segmenting the photovoltaic panel image at the jth moment in the ith area, extracting the number of pixels with the gray values of the pixels larger than the pixel segmentation threshold T, and taking the ratio of the number of pixels with the gray values of the pixels larger than the pixel segmentation threshold T to the number of all pixels of the photovoltaic panel image at the jth moment in the ith areaThe dirt specific gravity of the photovoltaic panel at the j moment serving as the i-th area;
S2026 based on the dirt specific gravity of the photovoltaic panel at the jth time of the ith region Calculating the dirt change value/>, of the photovoltaic panel at the j-th moment of the i-th area。
Specifically, the specific steps of calculating the weather change data and the reflectivity change data of all the areas include:
s401, setting the wind speed at the jth moment of the ith area as Humidity is/>Air quality index is/>; The measured reflectivity of the photovoltaic panel at the jth moment of the ith area is/>；
S402, respectively calculating the wind speed change value of the jth moment of the ith areaHumidity change value/>Air quality index change value/>Reflectance change value；
S403, taking the wind speed change value at the jth moment of the ith area, the humidity change value at the jth moment of the ith area and the air quality index change value at the jth moment of the ith area as weather change data at the jth moment of the ith area, and taking the reflectivity change value at the jth moment of the ith area as reflectivity change data at the jth moment of the ith area.
Specifically, the specific steps of constructing the cleanliness detection model based on the weather change data, the reflectivity change data and the cleanliness characteristic information include:
s501, establishing a cleanliness detection set A for storing weather change data, reflectivity change data and cleaning characteristic information of m areas at n moments, wherein the cleaning characteristic information comprises a photovoltaic panel dust coverage value and a photovoltaic panel dirt change value;
s502, dividing the cleanliness detection set A into a cleanliness detection training set and a cleanliness detection test set;
S503, constructing a cleanliness detection regression network, taking weather change data and reflectivity change data in a cleanliness detection training set as input of the cleanliness detection regression network, taking cleaning characteristic information in the cleanliness detection training set as output of the cleanliness detection regression network, and training the cleanliness detection regression network to obtain a photovoltaic panel cleanliness detection regression network;
And S504, performing model verification on the photovoltaic panel cleanliness detection regression network by using the cleanliness detection test set, and outputting the photovoltaic panel cleanliness detection regression network with the accuracy greater than or equal to the preset model test accuracy as a cleanliness detection model.
A photovoltaic panel cleanliness detection system for implementing the photovoltaic panel cleanliness detection method, the system comprising:
The image acquisition module is used for acquiring the image of the photovoltaic panel of each region based on the photovoltaic power station divided into m regions, wherein each region at least comprises one photovoltaic panel, fixed shooting points are set, and the photovoltaic panels of each region are subjected to image acquisition to acquire the image of the photovoltaic panel of each region;
the cleaning characteristic information acquisition module is used for preprocessing the acquired photovoltaic panel image and acquiring cleaning characteristic information in the photovoltaic panel image;
The data acquisition module is used for acquiring weather data of all areas and measuring the reflectivity of the photovoltaic panels in all areas;
The data analysis module is used for calculating weather change data and reflectivity change data of all areas;
the cleanliness detection model construction module is used for constructing a cleanliness detection model based on weather change data, reflectivity change data and cleaning characteristic information;
the cleanliness detection result feedback module is used for detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result;
and the control module is used for controlling the operation of each module.
Compared with the prior art, the invention has the following beneficial effects:
Dividing a photovoltaic power station into m areas, wherein each area at least comprises a photovoltaic panel, setting fixed shooting points, and acquiring images of the photovoltaic panels in each area to obtain photovoltaic panel images in each area; preprocessing the obtained photovoltaic panel image to obtain cleaning characteristic information in the photovoltaic panel image; acquiring weather data of all areas, and measuring the reflectivity of the photovoltaic panels in all areas; calculating weather change data and reflectivity change data of all areas; constructing a cleanliness detection model based on the weather change data, the reflectivity change data and the cleaning characteristic information; and detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result. According to the invention, by analyzing weather changes and the reflection condition of the surface of the photovoltaic panel, larger errors existing in the detection of the cleanliness of the photovoltaic panel by using machine vision are further reduced.
Drawings
FIG. 1 is a flow chart of a method for detecting cleanliness of a photovoltaic panel according to the present invention;
fig. 2 is a block diagram of a system for detecting cleanliness of a photovoltaic panel according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
The embodiment provides a method for detecting the cleanliness of a photovoltaic panel, which specifically comprises the following specific steps as shown in fig. 1:
S1, dividing a photovoltaic power station into m areas, wherein each area at least comprises a photovoltaic panel, setting fixed shooting points, and acquiring images of the photovoltaic panels in each area to obtain the images of the photovoltaic panels in each area;
s2, preprocessing the obtained photovoltaic panel image to obtain cleaning characteristic information in the photovoltaic panel image;
s3, weather data of all areas are obtained, and reflectivity of the photovoltaic panels in all areas is measured;
s4, calculating weather change data and reflectivity change data of all areas based on the step S3;
s5, constructing a cleanliness detection model based on weather change data, reflectivity change data and cleaning characteristic information;
And S6, detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result.
In this embodiment, the acquiring the photovoltaic panel image of each region in S1 includes acquiring the photovoltaic panel images of each region at n times.
In this embodiment, the preprocessing in S2 includes: image denoising operation and image enhancement operation.
In this embodiment, the step S2 of acquiring the cleaning feature information in the photovoltaic panel image specifically includes the following steps:
s201, calculating a dust coverage value of the photovoltaic panel based on the photovoltaic panel images of each region at n moments;
S202, threshold segmentation is carried out on the preprocessed photovoltaic panel images at n times in each region, the photovoltaic panel images are segmented into dirt images and background images, and dirt change values of the photovoltaic panels are calculated;
And S203, taking the dust coverage value of the photovoltaic panel and the dirt change value of the photovoltaic panel as cleaning characteristic information.
Specifically, the step of obtaining weather data of all the areas in S3 includes: acquiring wind speed, humidity and air quality indexes of each region at n moments; the measuring the reflectivity of the photovoltaic panel in all areas includes: the reflectivity of the photovoltaic panel was measured at n times per zone.
In this embodiment, the step S201 includes the following specific steps:
s2011, traversing all pixel points in the photovoltaic panel image at the jth moment of the ith area, and acquiring color vectors of all pixel points, wherein i is any one of 1 to m, and j is any one of 1 to n;
S2012, setting the Q pixel points in the photovoltaic panel image at the jth moment of the ith area, wherein the color vector of the qth pixel point is as follows Wherein/>For the color value of the red channel in the color vector of the q-th pixel point,/>For the color value of the green channel in the color vector of the q-th pixel point,/>A color value of a blue channel in a color vector for a qth pixel, Q being any one of 1 to Q;
S2013, calculating the dust coverage value of the photovoltaic panel at the j-th moment of the i-th area Wherein Q is any one of 1 to Q, when q=1,/>、/>、/>All 0.
In this embodiment, the specific step of calculating the dirt change value of the photovoltaic panel includes:
s2021, setting a pixel segmentation threshold value as T, and carrying out threshold segmentation on the preprocessed photovoltaic panel images at n times in each region;
S2022, carrying out graying treatment on the photovoltaic panel image at n times in each region, and extracting gray values corresponding to all pixel points in the image, wherein the gray value of the q-th pixel point in the photovoltaic panel image at the j-th time in the ith region is ；
S2023, counting the pixel points with the gray values smaller than or equal to the pixel segmentation threshold T and the pixel points with the gray values larger than the pixel segmentation threshold T; setting total Q1 pixel points with gray values less than or equal to the pixel division threshold T, wherein the gray value of the Q1 pixel point isQ1 is any one of 1 to Q1; the total number of the pixel points with the Q2 gray values larger than the pixel division threshold T is Q2, wherein the gray value of the Q2 th pixel point is/>Q2 is any one of 1 to Q2;
s2024 calculating the intraclass variance using the intraclass variance calculation formula Acquiring a pixel segmentation threshold T with the smallest intra-class variance as a dirt segmentation threshold of the photovoltaic panel image at the jth moment of the ith area; wherein the intra-class variance calculation formula is；
S2025, based on the dirt segmentation threshold T of the photovoltaic panel image at the jth moment in the ith area, segmenting the photovoltaic panel image at the jth moment in the ith area, extracting the number of pixels with the gray values of the pixels larger than the pixel segmentation threshold T, and taking the ratio of the number of pixels with the gray values of the pixels larger than the pixel segmentation threshold T to the number of all pixels of the photovoltaic panel image at the jth moment in the ith areaThe dirt specific gravity of the photovoltaic panel at the j moment serving as the i-th area;
S2026 based on the dirt specific gravity of the photovoltaic panel at the jth time of the ith region Calculating the dirt change value/>, of the photovoltaic panel at the j-th moment of the i-th area。
In this embodiment, the specific steps of calculating the weather change data and the reflectance change data of all the areas include:
s401, setting the wind speed at the jth moment of the ith area as Humidity is/>Air quality index is/>; The measured reflectivity of the photovoltaic panel at the jth moment of the ith area is/>；
S402, respectively calculating the wind speed change value of the jth moment of the ith areaValue of humidity changeAir quality index change value/>Reflectance change value/>；
S403, taking the wind speed change value at the jth moment of the ith area, the humidity change value at the jth moment of the ith area and the air quality index change value at the jth moment of the ith area as weather change data at the jth moment of the ith area, and taking the reflectivity change value at the jth moment of the ith area as reflectivity change data at the jth moment of the ith area.
In this embodiment, the specific steps of constructing the cleanliness detection model based on the weather variation data, the reflectivity variation data and the cleanliness feature information include:
s501, establishing a cleanliness detection set A for storing weather change data, reflectivity change data and cleaning characteristic information of m areas at n moments, wherein the cleaning characteristic information comprises a photovoltaic panel dust coverage value and a photovoltaic panel dirt change value;
s502, dividing the cleanliness detection set A into a cleanliness detection training set and a cleanliness detection test set;
S503, constructing a cleanliness detection regression network, taking weather change data and reflectivity change data in a cleanliness detection training set as input of the cleanliness detection regression network, taking cleaning characteristic information in the cleanliness detection training set as output of the cleanliness detection regression network, and training the cleanliness detection regression network to obtain a photovoltaic panel cleanliness detection regression network;
And S504, performing model verification on the photovoltaic panel cleanliness detection regression network by using the cleanliness detection test set, and outputting the photovoltaic panel cleanliness detection regression network with the accuracy greater than or equal to the preset model test accuracy as a cleanliness detection model.
Example 2
The present embodiment provides a photovoltaic panel cleanliness detection system for implementing a photovoltaic panel cleanliness detection method described in embodiment 1, as shown in fig. 2, the system includes:
The image acquisition module is used for acquiring the image of the photovoltaic panel of each region based on the photovoltaic power station divided into m regions, wherein each region at least comprises one photovoltaic panel, fixed shooting points are set, and the photovoltaic panels of each region are subjected to image acquisition to acquire the image of the photovoltaic panel of each region;
the cleaning characteristic information acquisition module is used for preprocessing the acquired photovoltaic panel image and acquiring cleaning characteristic information in the photovoltaic panel image;
The data acquisition module is used for acquiring weather data of all areas and measuring the reflectivity of the photovoltaic panels in all areas;
The data analysis module is used for calculating weather change data and reflectivity change data of all areas;
the cleanliness detection model construction module is used for constructing a cleanliness detection model based on weather change data, reflectivity change data and cleaning characteristic information;
the cleanliness detection result feedback module is used for detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result;
and the control module is used for controlling the operation of each module.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (4)
1. A method for detecting cleanliness of a photovoltaic panel is characterized by comprising the following steps of: the method comprises the following specific steps:
S1, dividing a photovoltaic power station into m areas, wherein each area at least comprises a photovoltaic panel, setting fixed shooting points, and acquiring images of the photovoltaic panels in each area to obtain the images of the photovoltaic panels in each area;
s2, preprocessing the obtained photovoltaic panel image to obtain cleaning characteristic information in the photovoltaic panel image;
s3, weather data of all areas are obtained, and reflectivity of the photovoltaic panels in all areas is measured;
s4, calculating weather change data and reflectivity change data of all areas based on the step S3;
s5, constructing a cleanliness detection model based on weather change data, reflectivity change data and cleaning characteristic information;
S6, detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result;
the step S2 of acquiring the cleaning characteristic information in the photovoltaic panel image specifically comprises the following steps:
s201, calculating a dust coverage value of the photovoltaic panel based on the photovoltaic panel images of each region at n moments;
The step S201 comprises the following specific steps:
s2011, traversing all pixel points in the photovoltaic panel image at the jth moment of the ith area, and acquiring color vectors of all pixel points, wherein i is any one of 1 to m, and j is any one of 1 to n;
S2012, setting the Q pixel points in the photovoltaic panel image at the jth moment of the ith area, wherein the color vector of the qth pixel point is as follows Wherein/>For the color value of the red channel in the color vector of the q-th pixel point,/>For the color value of the green channel in the color vector of the q-th pixel point,/>A color value of a blue channel in a color vector for a qth pixel, Q being any one of 1 to Q;
S2013, calculating the dust coverage value of the photovoltaic panel at the j-th moment of the i-th area Wherein Q is any one of 1 to Q, when q=1,/>、、/>Are all 0;
The step of obtaining weather data of all areas in S3 includes: acquiring wind speed, humidity and air quality indexes of each region at n moments; the measuring the reflectivity of the photovoltaic panel in all areas includes: measuring the reflectivity of the photovoltaic panel at n times in each region;
The step S2 of acquiring the cleaning characteristic information in the photovoltaic panel image specifically further comprises the following steps:
S202, threshold segmentation is carried out on the preprocessed photovoltaic panel images at n times in each region, the photovoltaic panel images are segmented into dirt images and background images, and dirt change values of the photovoltaic panels are calculated;
S203, taking the dust coverage value of the photovoltaic panel and the dirt change value of the photovoltaic panel as cleaning characteristic information;
the specific steps for calculating the dirt change value of the photovoltaic panel comprise the following steps:
s2021, setting a pixel segmentation threshold value as T, and carrying out threshold segmentation on the preprocessed photovoltaic panel images at n times in each region;
S2022, carrying out graying treatment on the photovoltaic panel image at n times in each region, and extracting gray values corresponding to all pixel points in the image, wherein the gray value of the q-th pixel point in the photovoltaic panel image at the j-th time in the ith region is ；
S2023, counting the pixel points with the gray values smaller than or equal to the pixel segmentation threshold T and the pixel points with the gray values larger than the pixel segmentation threshold T; setting total Q1 pixel points with gray values less than or equal to the pixel division threshold T, wherein the gray value of the Q1 pixel point isQ1 is any one of 1 to Q1; the total number of the pixel points with the Q2 gray values larger than the pixel division threshold T is Q2, wherein the gray value of the Q2 th pixel point is/>Q2 is any one of 1 to Q2;
s2024 calculating the intraclass variance using the intraclass variance calculation formula Acquiring a pixel segmentation threshold T with the smallest intra-class variance as a dirt segmentation threshold of the photovoltaic panel image at the jth moment of the ith area; wherein the intra-class variance calculation formula is；
S2025, based on the dirt segmentation threshold T of the photovoltaic panel image at the jth moment in the ith area, segmenting the photovoltaic panel image at the jth moment in the ith area, extracting the number of pixels with the gray values of the pixels larger than the pixel segmentation threshold T, and taking the ratio of the number of pixels with the gray values of the pixels larger than the pixel segmentation threshold T to the number of all pixels of the photovoltaic panel image at the jth moment in the ith areaThe dirt specific gravity of the photovoltaic panel at the j moment serving as the i-th area;
S2026 based on the dirt specific gravity of the photovoltaic panel at the jth time of the ith region Calculating the dirt change value/>, of the photovoltaic panel at the j-th moment of the i-th area；
The specific steps of calculating the weather change data and the reflectivity change data of all areas comprise:
s401, setting the wind speed at the jth moment of the ith area as Humidity is/>Air quality index is/>; The measured reflectivity of the photovoltaic panel at the jth moment of the ith area is/>；
S402, respectively calculating the wind speed change value of the jth moment of the ith areaValue of humidity changeAir quality index change value/>Reflectance change value/>；
S403, taking the wind speed change value at the jth moment of the ith area, the humidity change value at the jth moment of the ith area and the air quality index change value at the jth moment of the ith area as weather change data at the jth moment of the ith area, and taking the reflectivity change value at the jth moment of the ith area as reflectivity change data at the jth moment of the ith area.
2. The method for detecting the cleanliness of a photovoltaic panel according to claim 1, wherein: the preprocessing in S2 includes: image denoising operation and image enhancement operation.
3. The method for detecting the cleanliness of a photovoltaic panel according to claim 2, wherein: the specific steps of constructing the cleanliness detection model based on the weather change data, the reflectivity change data and the cleanliness characteristic information include:
s501, establishing a cleanliness detection set A for storing weather change data, reflectivity change data and cleaning characteristic information of m areas at n moments, wherein the cleaning characteristic information comprises a photovoltaic panel dust coverage value and a photovoltaic panel dirt change value;
s502, dividing the cleanliness detection set A into a cleanliness detection training set and a cleanliness detection test set;
S503, constructing a cleanliness detection regression network, taking weather change data and reflectivity change data in a cleanliness detection training set as input of the cleanliness detection regression network, taking cleaning characteristic information in the cleanliness detection training set as output of the cleanliness detection regression network, and training the cleanliness detection regression network to obtain a photovoltaic panel cleanliness detection regression network;
And S504, performing model verification on the photovoltaic panel cleanliness detection regression network by using the cleanliness detection test set, and outputting the photovoltaic panel cleanliness detection regression network with the accuracy greater than or equal to the preset model test accuracy as a cleanliness detection model.
4. A photovoltaic panel cleanliness detection system for implementing a photovoltaic panel cleanliness detection method according to any one of claims 1-3, characterized in that: the system comprises:
The image acquisition module is used for acquiring the image of the photovoltaic panel of each region based on the photovoltaic power station divided into m regions, wherein each region at least comprises one photovoltaic panel, fixed shooting points are set, and the photovoltaic panels of each region are subjected to image acquisition to acquire the image of the photovoltaic panel of each region;
the cleaning characteristic information acquisition module is used for preprocessing the acquired photovoltaic panel image and acquiring cleaning characteristic information in the photovoltaic panel image;
The data acquisition module is used for acquiring weather data of all areas and measuring the reflectivity of the photovoltaic panels in all areas;
The data analysis module is used for calculating weather change data and reflectivity change data of all areas;
the cleanliness detection model construction module is used for constructing a cleanliness detection model based on weather change data, reflectivity change data and cleaning characteristic information;
the cleanliness detection result feedback module is used for detecting the cleanliness of the photovoltaic panel based on the cleanliness detection model to obtain a cleanliness detection result;
and the control module is used for controlling the operation of each module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410303697.3A CN117895899B (en) | 2024-03-18 | 2024-03-18 | Photovoltaic panel cleanliness detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410303697.3A CN117895899B (en) | 2024-03-18 | 2024-03-18 | Photovoltaic panel cleanliness detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117895899A CN117895899A (en) | 2024-04-16 |
| CN117895899B true CN117895899B (en) | 2024-05-31 |
Family
ID=90641697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410303697.3A Active CN117895899B (en) | 2024-03-18 | 2024-03-18 | Photovoltaic panel cleanliness detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117895899B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012159375A (en) * | 2011-01-31 | 2012-08-23 | Fujitsu Ltd | Reflectance calculation device, reflectance calculation method, and program |
| CN107727145A (en) * | 2017-10-10 | 2018-02-23 | 国网江苏省电力公司电力科学研究院 | A kind of distributed power source state monitoring apparatus and method based on Internet of Things |
| CN111740699A (en) * | 2020-05-29 | 2020-10-02 | 南京航空航天大学 | Photovoltaic panel fault detection and identification method and device and unmanned aerial vehicle |
| CN115512290A (en) * | 2022-08-23 | 2022-12-23 | 中国华能集团清洁能源技术研究院有限公司 | Photovoltaic panel efficiency monitoring method and system based on image recognition technology |
| CN116993747A (en) * | 2023-09-28 | 2023-11-03 | 徐州太一世纪能源科技有限公司 | Unmanned aerial vehicle-based solar photovoltaic panel surface cleanliness analysis method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230042106A1 (en) * | 2019-12-09 | 2023-02-09 | Universidad Técnica Federico Santa María | System and method for the statistical analysis of images of photovoltaic panels |
| FR3113780A1 (en) * | 2020-09-03 | 2022-03-04 | Acpv | Electricity production module |
-
2024
- 2024-03-18 CN CN202410303697.3A patent/CN117895899B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012159375A (en) * | 2011-01-31 | 2012-08-23 | Fujitsu Ltd | Reflectance calculation device, reflectance calculation method, and program |
| CN107727145A (en) * | 2017-10-10 | 2018-02-23 | 国网江苏省电力公司电力科学研究院 | A kind of distributed power source state monitoring apparatus and method based on Internet of Things |
| CN111740699A (en) * | 2020-05-29 | 2020-10-02 | 南京航空航天大学 | Photovoltaic panel fault detection and identification method and device and unmanned aerial vehicle |
| CN115512290A (en) * | 2022-08-23 | 2022-12-23 | 中国华能集团清洁能源技术研究院有限公司 | Photovoltaic panel efficiency monitoring method and system based on image recognition technology |
| CN116993747A (en) * | 2023-09-28 | 2023-11-03 | 徐州太一世纪能源科技有限公司 | Unmanned aerial vehicle-based solar photovoltaic panel surface cleanliness analysis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117895899A (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110310261B (en) | Contact net dropper defect detection model training method and defect detection method | |
| CN106875373B (en) | Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm | |
| WO2020199538A1 (en) | Bridge key component disease early-warning system and method based on image monitoring data | |
| CN111784633B (en) | Insulator defect automatic detection algorithm for electric power inspection video | |
| CN109584227A (en) | A kind of quality of welding spot detection method and its realization system based on deep learning algorithm of target detection | |
| CN107229929A (en) | A kind of license plate locating method based on R CNN | |
| CN109559310A (en) | Power transmission and transformation inspection image quality evaluating method and system based on conspicuousness detection | |
| CN113344475B (en) | Transformer bushing defect identification method and system based on sequence modal decomposition | |
| CN112396635B (en) | Multi-target detection method based on multiple devices in complex environment | |
| CN103344583A (en) | Praseodymium-neodymium (Pr/Nd) component content detection system and method based on machine vision | |
| CN106839976A (en) | A kind of method and device at detector lens center | |
| CN102456142A (en) | Analysis method for smoke blackness based on computer vision | |
| CN106651906A (en) | Test method for motion characteristic of high-voltage breaker based on improved Gaussian mixture model | |
| CN111896549A (en) | Building crack monitoring system and method based on machine learning | |
| CN112699824A (en) | Method and device for detecting constant of electric energy meter and storage medium | |
| CN110567967B (en) | Display panel detection method, system, terminal device and computer readable medium | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN108921826A (en) | The transmission line of electricity that super-pixel segmentation is combined with deep learning invades object detecting method | |
| CN111540203A (en) | Method for adjusting green light passing time based on fast-RCNN | |
| CN113706496B (en) | Aircraft structure crack detection method based on deep learning model | |
| CN117895899B (en) | Photovoltaic panel cleanliness detection method and system | |
| CN117522833A (en) | Camera resolution evaluation method and device, electronic equipment and storage medium | |
| CN113627302A (en) | Method and system for detecting compliance of ascending construction | |
| CN110518881B (en) | Hot spot monitoring device and prediction method based on environmental meteorological factors | |
| KR102172968B1 (en) | Apparatus and method for determining faults of line |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |